scholar-mcp
Allows the Gemma 4 agent running on Ollama to use retrieval tools via MCP for answering questions about book content.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
little-librarian
A local MCP server that indexes .epub files and exposes semantic search tools
backed by pplx-embed-context-v1 (late chunking) and Qdrant.
MCP client (Claude Desktop, Claude Code, …)
│
▼ tool calls via MCP
server.py
pplx-embed-context-v1-0.6b + Qdrant (local)Files
File | Role |
| MCP server — epub ingestion, embedding, search, Qdrant storage |
| Separate MCP server for code (AST-based chunking) |
Related MCP server: ragi
Why pplx-embed-context-v1
Uses late chunking: all chunks from a chapter go through a single forward pass, so each chunk embedding captures full document context without needing a doc-prefix at inference time. Scores 81.96 nDCG@10 on ConTEB.
Quick start
# 1. install
pip install -e .
# 2. ingest your library (runs embedding, then exits)
HF_HUB_OFFLINE=0 python server.py --index ./library
# 3. start the MCP server
python server.py
# optional: preload the model at startup
python server.py --preloadMCP tools
Tool | Description |
| Semantic search, returns top-k passages with scores |
| Search grouped by |
| Retrieve full text for a book/chapter |
| List all indexed books with chapter counts |
| Qdrant collection info (point count, vector size) |
| Full content breakdown: books, chapters, chunks per book, avg chunk length |
| Show which device (CPU/GPU) is used for embeddings |
Claude Desktop config
{
"mcpServers": {
"little-librarian": {
"command": "python",
"args": ["/path/to/server.py"]
}
}
}Hardware guidance
Setup | Min VRAM |
CPU only | 0 GB |
GPU (pplx-embed-0.6b) | ~2 GB |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
An MCP server for search and retrieval over a local LanceDB database
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Remote ChromaDB vector database MCP server with streamable HTTP transport
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceLocal MCP server that provides semantic search (RAG) over code repositories, enabling AI clients like Claude and Gemini to access project context without manual re-upload.-
- AlicenseAqualityDmaintenanceLocal-first RAG indexing and semantic search MCP server. Enables document retrieval and context-aware queries using local embedding models.38 npmMIT
- AlicenseNot gradedqualityBmaintenanceMCP server for local RAG over personal notes, PDFs, and documents, enabling plain-English querying and hybrid search with multi-hop context expansion.MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for querying a personal knowledge base using semantic RAG, powered by DeepSeek and local embeddings from Ollama.-